hoya012/deep_learning_object_detection

★ 11,400PythonAudience · researcherComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((Object Detection Papers))
    Coverage
      2014 to 2020
      Top conferences
      Major methods
    Key methods
      R-CNN family
      YOLO versions
      SSD
      RetinaNet
    Resources
      Paper links
      Code links
      Benchmark table
    Conferences
      CVPR
      ICCV
      NeurIPS

mindmap root((Object Detection Papers)) Coverage 2014 to 2020 Top conferences Major methods Key methods R-CNN family YOLO versions SSD RetinaNet Resources Paper links Code links Benchmark table Conferences CVPR ICCV NeurIPS

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Survey the history of deep learning object detection from R-CNN through YOLO and other major methods up to 2020.

USE CASE 2

Compare accuracy scores across different detection methods using the VOC and COCO benchmark table in one place.

USE CASE 3

Find links to original papers and code implementations for a specific object detection approach you want to study or reproduce.

Getting it running

Difficulty · easy Time to first run · 5min

In plain English

This repository is a curated reading list of academic research papers on object detection using deep learning (the branch of AI that teaches computers to recognize things in images and video). It is not a tool you install and run. It is a reference resource maintained by one researcher for others who want to follow the history and progress of this field. Object detection is the task of not just recognizing what is in an image, but also drawing boxes around each thing (a cat, a person, a car) and labeling them. The papers in this list cover major methods developed from 2014 onward, including well-known approaches like R-CNN, YOLO, SSD, and RetinaNet, as well as many others from top research conferences such as CVPR, ICCV, ECCV, and NeurIPS. The README includes a visual timeline diagram showing how detection methods evolved year by year, and a large performance comparison table. The table shows how different detectors score on standard benchmark datasets (VOC and COCO), giving researchers a quick way to compare methods. Each entry in the paper list includes a link to the original paper and, where available, links to official or community code implementations. The list was actively maintained from 2018 through September 2020, with monthly or quarterly updates adding newly published work. After that date, no further updates are shown in the log. This repository is useful for researchers, students, or developers who want a structured entry point into the object detection literature, or who need to survey what methods existed up to 2020. There is no installation or code to run. The full README is longer than what was shown.

Copy-paste prompts

Prompt 1

Based on this object detection paper survey, which method should I start with for detecting objects in real-time video on a CPU? Compare the YOLO versions and SSD.

Prompt 2

I'm new to object detection research. Using this paper list as a guide, explain the difference between one-stage and two-stage detectors like SSD versus Faster R-CNN.

Prompt 3

Which object detection methods in this list have the best COCO benchmark accuracy, and where can I find their official code?

Open on GitHub → Explain another repo

← hoya012 on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.